UnpicklingError: invalid load key, 'v'.

[LayanNCAI]

Hello,

after running this command:
python3 -m fastchat.model.apply_delta --base-model-path ./llama-13b-hf --target-model-path ./vicuna-13b --delta-path ./vicuna-13b-delta-v0/

I get this:

Loading the base model from ./llama-13b-hf
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 41/41 [00:51<00:00,  1.25s/it]
Loading the delta from ./vicuna-13b-delta-v0/
Loading checkpoint shards:   0%|                                                                                                                                                     | 0/3 [00:00<?, ?it/s]

then:

UnpicklingError: invalid load key, 'v'.

During handling of the above exception, another exception occurred:
OSError: You seem to have cloned a repository without having git-lfs installed. Please install git-lfs and run `git lfs install` followed by `git lfs pull` in the folder you cloned.

Any idea why that would happen? I deleted and installed the llama and vicuna files multiple times but nothing worked.

[LayanNCAI]

when I ran the same command on my local machine this is what I got:

Loading the base model from ./llama-13b-hf
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 41/41 [00:17<00:00,  2.30it/s]
Loading the delta from ./vicuna-13b-delta-v0/
Loading checkpoint shards:  33%|███████████████████████████████████████████████                                                                                              | 1/3 [00:04<00:08,  4.10s/it]
Killed

[LayanNCAI]

when I ran the same command on my local machine this is what I got:

Loading the base model from ./llama-13b-hf
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 41/41 [00:17<00:00,  2.30it/s]
Loading the delta from ./vicuna-13b-delta-v0/
Loading checkpoint shards:  33%|███████████████████████████████████████████████                                                                                              | 1/3 [00:04<00:08,  4.10s/it]
Killed

for this issue I fixed it by increasing the swap file size to 16G, reference

then I got this error:
ValueError: Tokenizer class LLaMATokenizer does not exist or is not currently imported.
which was fixed by changing the tokenizer name in "llama-13b-hf/tokenizer_config.json " to LlamaTokenizer for more on this: huggingface/transformers#22222 (comment)

[luofeng1994]

I had the same problem, did you solve it。